From 7680fd689ecf7d11bf2dfdba41dc2f33cde2bbe7 Mon Sep 17 00:00:00 2001 From: Konsta Holtta Date: Tue, 16 May 2017 13:47:58 +0300 Subject: gpu: nvgpu: hold power ref for deterministic channels To support deterministic channels even with platforms where railgating is supported, have each deterministic-marked channel hold a power reference during their lifetime, and skip taking power refs for jobs in submit path for those. Previously, railgating blocked deterministic submits in general because of gk20a_busy()/gk20a_idle() calls in submit path possibly taking time and more significantly because the gpu may need turning on which takes a nondeterministic and long amount of time. As an exception, gk20a_do_idle() can still block deterministic submits until gk20a_do_unidle() is called. Add a rwsem to guard this. VPR resize needs do_idle, which conflicts with deterministic channels' requirement to keep the GPU on. This is documented in the ioctl header now. Make NVGPU_GPU_FLAGS_SUPPORT_DETERMINISTIC_SUBMIT_NO_JOBTRACKING always set in the gpu characteristics now that it's supported. The only thing left now blocking NVGPU_GPU_FLAGS_SUPPORT_DETERMINISTIC_SUBMIT_FULL is the sync framework. Make the channel debug dump show which channels are deterministic. Bug 200291300 Jira NVGPU-70 Change-Id: I47b6f3a8517cd6e4255f6ca2855e3dd912e4f5f3 Signed-off-by: Konsta Holtta Reviewed-on: http://git-master/r/1483038 Reviewed-by: mobile promotions Tested-by: mobile promotions --- drivers/gpu/nvgpu/gk20a/fifo_gk20a.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/nvgpu/gk20a/fifo_gk20a.c') diff --git a/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c b/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c index 5a571dc8..37e19ef8 100644 --- a/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c +++ b/drivers/gpu/nvgpu/gk20a/fifo_gk20a.c @@ -3494,10 +3494,11 @@ void gk20a_dump_channel_status_ramfc(struct gk20a *g, syncpointa = inst_mem[ram_fc_syncpointa_w()]; syncpointb = inst_mem[ram_fc_syncpointb_w()]; - gk20a_debug_output(o, "%d-%s, pid %d, refs: %d: ", hw_chid, + gk20a_debug_output(o, "%d-%s, pid %d, refs %d%s: ", hw_chid, g->name, ch_state->pid, - ch_state->refs); + ch_state->refs, + ch_state->deterministic ? ", deterministic" : ""); gk20a_debug_output(o, "channel status: %s in use %s %s\n", ccsr_channel_enable_v(channel) ? "" : "not", gk20a_decode_ccsr_chan_status(status), @@ -3576,6 +3577,7 @@ void gk20a_debug_dump_all_channel_status_ramfc(struct gk20a *g, ch_state[chid]->pid = ch->pid; ch_state[chid]->refs = atomic_read(&ch->ref_count); + ch_state[chid]->deterministic = ch->deterministic; nvgpu_mem_rd_n(g, &ch->inst_block, 0, &ch_state[chid]->inst_block[0], ram_in_alloc_size_v()); -- cgit v1.2.2